© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37184
    Prev
    Next
    INDEX
    Explanations

    direction and location references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¡
    -0.11
    主ä¸ļ
    -0.09
    èĭŀ
    -0.09
    个åŁİå¸Ĥ
    -0.08
    _again
    -0.08
    åĨį次
    -0.08
    ä¸įåħį
    -0.08
     Cort
    -0.08
    åĨįä¸Ģ次
    -0.08
    æīĢåľ¨
    -0.08
    POSITIVE LOGITS
    æĹģè¾¹
    0.13
    ä¸İæѤ
    0.12
    ä½įäºİ
    0.12
     nearby
    0.11
    ä½įæĸ¼
    0.11
    åıijçĶŁåľ¨
    0.11
    åĽĽåij¨
    0.11
    åľ¨ä»ĸ
    0.10
    åij¨åĽ´
    0.10
    å°±åľ¨
    0.10
    Activations Density 0.250%

    No Known Activations